Bioinformatics/psychiatric genetics PhD candidate @CompMedUCLA | @ucla CompBio+Math alum | Here mainly for science + NBA twitter & geography memes. (he/him)
Los Angeles, CA
Joined November 2014
- Tweets162
- Following475
- Followers227
- Likes1.3K
Aditya Pimplaskar retweeted
A new preprint from Gerdes et al. reports an exome-wide association study of serious mental illness in ~42,000 individuals from the Paisa, a founder population in Colombia. A deep dive below on why it fills a gap population-scale sequencing never could.
Aditya Pimplaskar retweeted
Concerned about the AI slop heading to ICLR ? The @uclaNLP submissions will be safe.
They are currently being handtyped by artisanal young researchers in a small-batch facility in the western lowlands of Los Angeles.
Aditya Pimplaskar retweeted
FastGxC: Fast and powerful context-specific eQTL mapping in bulk and single-cell data dlvr.it/TSbgrB
Aditya Pimplaskar retweeted
Interpretability has not kept up with scaling LLMs at all, especially for *knowledge*. But here's a wild idea:
using cross-lingual knowledge inconsistency (typically seen as a "bug") as a tool for dissecting where knowledge lives
🧵1/4 arxiv.org/abs/2603.17102 @GoogleResearch
Excited to see our work in AJHG! Thank you to our amazing co-authors, UCLA Institute for Precision Health, UCLA CTSI, and our collaborators for the support with this work. Above all, we are grateful to the patients and ATLAS biobank participants at @UCLAHealth.
🧬New today!
📄Inclusion bias affects common variant discovery and replication in a health-system linked biobank
🧑🤝🧑 @loldeloo @apimplaskar @bpasaniuc & co
cell.com/ajhg/fulltext/S0002…
Aditya Pimplaskar retweeted
New preprint! We mapped thalamocortical dynamics in human focal epilepsy using SEEG. We found distinct spectral and connectivity based signature that could be direct targets for neurostimulation.
With @UCLAMCH and @uclamii
medrxiv.org/content/10.64898…
Aditya Pimplaskar retweeted
"An hour of planning can save you 10 hours of doing."
✨📝 Planned Diffusion 📝 ✨ makes a plan before parallel dLLM generation.
Planned Diffusion runs 1.2-1.8× faster than autoregressive and an order of magnitude faster than diffusion, while staying within 0.9–5% AR quality.
Would love to connect/discuss projects w/ folks interested in EHR-based phenotyping methods for genetic studies, psychiatric genetics, and perinatal health!
#ASHG25
Excited to visit Boston for #ASHG25. I’ll be presenting our work on the effects of recruitment bias in biobank studies on Friday (10/17) @ board 1126 — please drop by and say hi!
Aditya Pimplaskar retweeted
🔦Adaptive Parallel Decoding (APD) has been accepted as a spotlight paper at @NeurIPSConf ! I thank my collaborators, reviewers, and program organizers for this honor.
A thread for those interested 🧵 (1/n)
Aditya Pimplaskar retweeted
Our work on genetic variants that affect RNA stability is out in @NatureGenet! We present the RNAtracker computational pipeline, which can distinguish between transcriptionally- vs. stability-mediated regulation of gene abundance. bit.ly/42aihk2 (1/n)
linking to the dictionary definition of luddite is such a humza thing to do -- this could never have been written by an LLM (i also love em dashes)
Aditya Pimplaskar retweeted
📣New from @bpasaniuc & co
📄Exploring #depression treatment response by using #polygenic risk scoring across diverse populations
cell.com/ajhg/abstract/S0002…
Aditya Pimplaskar retweeted
“That’s one small [MASK] for [MASK], a giant [MASK] for mankind.” – [MASK] Armstrong
Can autoregressive models predict the next [MASK]? It turns out yes, and quite easily…
Introducing MARIA (Masked and Autoregressive Infilling Architecture)
arxiv.org/abs/2502.06901
Aditya Pimplaskar retweeted
Does ambient RNA/DNA confound the genotype-based demultiplex of 10x Multi-ome data? Terence Li @terencewtli, a bioinfo grad student in Noah Zaitlen lab and my lab investigated precisely this question and provided practical recommendations.
The impact of ambient contamination on demultiplexing methods for single-nucleus multiome experiments biorxiv.org/content/10.1101/… #biorxiv_bioinfo
Aditya Pimplaskar retweeted
The impact of ambient contamination on demultiplexing methods for single-nucleus multiome experiments biorxiv.org/content/10.1101/… #biorxiv_bioinfo